scasella

Claude Dynamic Workflows Codex — AI skill for Claude Code

AI community

Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer.

How to install Claude Dynamic Workflows Codex

This entry records only its repository, not the path inside it, so there is no exact command to give. Open scasella/claude-dynamic-workflows-codex and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Dynamic Workflows Codex does

Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer.

Alternatives in AI

Fusion Plan — OMC interview (interactive) → 3-round Opus 4.8 + GPT-5.5 fusion deepening → concise .omc/plans/ output → revie 468 ★
Ataru — High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus 351 ★
Single File Wbs — 単一HTMLで動く WBS/ガント＋イナズマ線ビューア 123 ★

README

Claude Dynamic Workflows — on Codex

A **Claude Code skill**: type `/codex-workflows ` and a fleet of **Codex (GPT) agents** fans out across the work — Claude authors the workflow, runs it on your local `codex app-server`, and streams it back as a live **execution map**.

[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE) ![Node ≥ 18](https://img.shields.io/badge/node-%E2%89%A5%2018-green.svg) ![Dependencies: 0](https://img.shields.io/badge/dependencies-0-green.svg) [![CI](https://github.com/scasella/claude-dynamic-workflows-codex/actions/workflows/ci.yml/badge.svg)](https://github.com/scasella/claude-dynamic-workflows-codex/actions/workflows/ci.yml)

![Execution map](docs/map-dark.png)

↑ a real run: diagnose a checkout latency regression — triage the signals in parallel, **race three root-cause workers** and cancel the losers, steer the winner on its warm thread, then gate the fix. This is the bundled demo; open it yourself in 10 seconds ([below ↓](#see-it-now-no-codex-required)).

You describe a task; Claude Code writes a [dynamic-workflow](https://code.claude.com/docs/en/workflows) script — `agent()` / `parallel()` / `pipeline()` / `phase()` / `budget` — and runs it across dozens of GPT-5 agents instead of Claude subagents. The runtime holds the loop, branching, and intermediate results, so your context only sees the final answer — and you watch it build as an interactive map. And unlike the native one-shot DSL, workers here can stay **live** — steer a worker on warm context, race several and cancel the losers, or let a controller adapt the plan as results land ([Beyond one-shot ↓](#beyond-one-shot-sessionful-workers)). It scales one level up, too: add **`--multi`** and Claude launches a whole **fleet of concurrent workflows and supervises them itself** — answering their gates, steering, killing dead ends, forking winners ([walkthrough 8 ↓](#8--run-a-whole-fleet--and-let-claude-supervise-it)). Great for codebase a